Can't start training #2
Description
Hi, @ChristophReich1996, I can't start the training process.
After I execute python main.py --train, I got this
Traceback (most recent call last):
File "main.py", line 81, in <module>
model_wrapper.train(epochs=20)
File "/home/eason/research/DeepFovea++/model_wrapper.py", line 207, in train
self.discriminator_network(label),
File "/home/anaconda3/envs/deepfovea++/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/anaconda3/envs/deepfovea++/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 159, in forward
return self.module(*inputs[0], **kwargs[0])
File "/home/anaconda3/envs/deepfovea++/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/eason/research/DeepFovea++/discriminator.py", line 45, in forward
output = output.view(1, self.in_channels * 2, self.frames, output.shape[2], output.shape[3])
RuntimeError: shape '[1, 6, 6, 192, 256]' is invalid for input of size 3538944
I checked the prediction of the generator and the label and both of their dimension is [2, 18, 768, 1024]
I'm not sure if there's anything missing.
(By the way, I successfully executed validation.)
Thanks.